Method, System and Apparatus for Classification of Objects in a Radar System

Abstract

According to an aspect, a radar system comprising a transmitter transmitting a radar signal, a receiver receiving a reflected signal that is a reflection of the radar signal from a plurality of objects, in that the receiver is configured generate a point cloud comprising plurality of points with each point representing a range, a velocity and a position information, a feature extension unit configured to generate a plurality of tracks from the point cloud with each track comprising a corresponding set of points and generating an extended feature set for each track, in that each track representing an object in the plurality of objects and a classifier classifying the plurality of tracks into a set of classes using a reference data derived from the range, the velocity, the position information and the extended features.

What is claimed is: 
     
         1 . A radar system comprising:
 a transmitter transmitting a radar signal;   a receiver receiving a reflected signal that is a reflection of the radar signal from a plurality of objects, in that the receiver is configured to generate a point cloud comprising plurality of points with each point representing a range, a velocity, an angle and a signal to noise ratio (SNR) information;   a feature extraction unit configured to generate a plurality of tracks from the point cloud and generating an extended feature set for each track, in that each track representing an object in the plurality of objects; and   a classifier classifying the plurality of tracks into a set of classes using a reference data derived from the range, the velocity, the position information and the extended features.   
     
     
         2 . The radar system of  claim 1 , where in the extended feature set comprising a width and a radar cross section (RCS) and the set of class comprising two-wheeler, cars and trucks, wherein plurality of tracks are generated by generating three clusters of points from the point cloud when arranged over the RCS and width. 
     
     
         3 . The radar system of  claim 1 , where in the feature extension unit is configured to generate the reference data. 
     
     
         4 . The radar system of  claim 3 , where in the feature extension unit is configured to select a first set of points from each cluster that are within a first distance from its centroid. 
     
     
         5 . The radar system of  claim 4 , where in the feature extension unit is configured to select a first set of points from each cluster when the centroids are separated by a threshold. 
     
     
         6 . A method of classifying a plurality of detected objects in a radar system comprising:
 receiving a reflected signal that is a reflection of a radar signal from a plurality of objects;   generating a point cloud, from the reflected signal, the point cloud comprising plurality of points with each point representing a range, a velocity, an angle and a signal to noise ratio (SNR) information;   grouping the plurality of points into clusters and compiling an extended feature list per cluster;   tracking each cluster and creating an associated feature set history per track;   collating an n-dimensional (n-D) feature space to form an n-D distribution of track points with each track as point in the space;   performing another clustering on a subset of n-D distribution of track points to generate a second set of clusters   identifying centroid of each cluster in the second set of cluster;   selecting a subset of samples around the centroid to form a training data per class; and   grouping training data per class and providing as learning examples to the classifier classifying the cluster into one of the classes.